© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14491
    Prev
    Next
    INDEX
    Explanations

    expressions related to legal terms and court proceedings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     CreateTagHelper
    -1.18
    AddTagHelper
    -1.16
     propOrder
    -1.15
    styleType
    -1.09
     Efq
    -1.07
    Personensuche
    -1.03
    SequentialGroup
    -1.01
     تضيفلها
    -0.98
    GEBURTSDATUM
    -0.96
     snippetHide
    -0.96
    POSITIVE LOGITS
    .
    0.56
    ib
    0.52
     for
    0.51
    ,
    0.48
     South
    0.47
     the
    0.46
     from
    0.46
     that
    0.44
     her
    0.44
     T
    0.44
    Activations Density 0.034%

    No Known Activations